User contributions for Fall2024 Wiki Team6
Jump to navigation
Jump to search
11 December 2024
- 20:0720:07, 11 December 2024 diff hist +1,665 Adafactor →Applications current Tag: Visual edit: Switched
- 20:0220:02, 11 December 2024 diff hist +2,024 Adafactor →Introduction Tag: Visual edit: Switched
- 19:5119:51, 11 December 2024 diff hist +21 Adafactor →Introduction
- 19:4919:49, 11 December 2024 diff hist +1,249 Adafactor →Introduction Tag: Visual edit: Switched
- 17:0217:02, 11 December 2024 diff hist −3 Adafactor →Numerical Examples Tag: Visual edit
- 16:5716:57, 11 December 2024 diff hist +329 Adafactor →Numerical Examples Tag: Visual edit
- 16:4416:44, 11 December 2024 diff hist +126 Adafactor →Numerical Examples Tag: Visual edit
- 16:2316:23, 11 December 2024 diff hist +615 Adafactor →Numerical Examples Tag: Visual edit
- 12:1012:10, 11 December 2024 diff hist +19 Adafactor →Numerical Examples Tag: Visual edit
- 02:0002:00, 11 December 2024 diff hist −11 Adafactor →Numerical Examples Tag: Visual edit
- 01:5801:58, 11 December 2024 diff hist +4,080 Adafactor →Numerical Examples Tag: Visual edit
10 December 2024
- 23:2623:26, 10 December 2024 diff hist −1,314 Adafactor →Numerical Examples Tag: Visual edit
- 23:2323:23, 10 December 2024 diff hist +2 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:2323:23, 10 December 2024 diff hist +2 Adafactor →Why Clipping
- 23:2323:23, 10 December 2024 diff hist +1 Adafactor →5.Discussion
- 23:2323:23, 10 December 2024 diff hist −1,013 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:2323:23, 10 December 2024 diff hist −507 Adafactor →Why Clipping
- 23:2223:22, 10 December 2024 diff hist +1,537 Adafactor →Problem formulation
- 23:2123:21, 10 December 2024 diff hist −16 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:2023:20, 10 December 2024 diff hist +2 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:1923:19, 10 December 2024 diff hist +117 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:1823:18, 10 December 2024 diff hist +7 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:1723:17, 10 December 2024 diff hist +97 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:1523:15, 10 December 2024 diff hist +281 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:0823:08, 10 December 2024 diff hist +54 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:0723:07, 10 December 2024 diff hist +13 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:0623:06, 10 December 2024 diff hist +180 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:0423:04, 10 December 2024 diff hist +2 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:0423:04, 10 December 2024 diff hist +197 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 23:0323:03, 10 December 2024 diff hist +13 Adafactor →Why Adafactor is more memory efficient, compared to Adam
- 22:5922:59, 10 December 2024 diff hist +68 Adafactor →Why Clipping
- 22:5422:54, 10 December 2024 diff hist +130 Adafactor →Why Clipping
- 22:5222:52, 10 December 2024 diff hist +379 Adafactor →Adafactor for Weighted Matrices
- 22:5222:52, 10 December 2024 diff hist −379 Adafactor →Why Clipping
- 22:5222:52, 10 December 2024 diff hist +4 Adafactor →Clipping
- 22:5122:51, 10 December 2024 diff hist +355 Adafactor →Clipping
- 22:4922:49, 10 December 2024 diff hist +19 Adafactor →2. Parameters
- 22:4522:45, 10 December 2024 diff hist +30 Adafactor →4. Proposed Hyperparameters for Adafactor
- 22:4522:45, 10 December 2024 diff hist +1,108 Adafactor →4. Proposed Hyperparameters for Adafactor
- 17:0017:00, 10 December 2024 diff hist −24 Adafactor →Adafactor for Weighted Matrices
- 16:5916:59, 10 December 2024 diff hist +6 Adafactor →Adafactor for Weighted Vectors
- 16:5916:59, 10 December 2024 diff hist −6 Adafactor →Adafactor for Weighted Vectors
- 16:5616:56, 10 December 2024 diff hist +5 Adafactor →Adafactor for Weighted Vectors Tag: Manual revert
- 16:5616:56, 10 December 2024 diff hist +1 Adafactor →Adafactor for Weighted Vectors
- 16:5516:55, 10 December 2024 diff hist −4 Adafactor →Adafactor for Weighted Vectors
- 16:5516:55, 10 December 2024 diff hist −2 Adafactor →Adafactor for Weighted Vectors
- 16:5416:54, 10 December 2024 diff hist −18 Adafactor →Adafactor for Weighted Vectors
- 16:5116:51, 10 December 2024 diff hist −9 Adafactor →3. Problem Formulation
- 16:5016:50, 10 December 2024 diff hist +4 Adafactor →2. Parameters
- 16:4916:49, 10 December 2024 diff hist +1 Adafactor →2. Parameters